Application of Deep Neural Networks for Clinical ECG-based Identification of Atrial Fibrosis
With the help of an existing algorithm, the P‑waves should first be extracted from clinical EKGs and features calculated. These features are intended to serve as input to a regression neural network that has been trained on simulated data to estimate the percentage of fibrosis in the atrium. Further machine learning techniques (e.g. LSTMs, CNNs) will then be applied to this problem and examined.